wu981526092 commited on
Commit
57efcbb
·
verified ·
1 Parent(s): 324e732

Upload 6 files

Browse files
Files changed (5) hide show
  1. config.json +16 -15
  2. model.safetensors +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +8 -6
  5. vocab.txt +0 -0
config.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
 
11
  "id2label": {
12
  "0": "No Poverty",
13
  "1": "Zero Hunger",
@@ -27,6 +27,7 @@
27
  "15": "Peace, Justice, and Strong Institutions"
28
  },
29
  "initializer_range": 0.02,
 
30
  "label2id": {
31
  "Affordable and Clean Energy": 6,
32
  "Clean Water and Sanitation": 5,
@@ -45,17 +46,17 @@
45
  "Sustainable Cites and Communities": 10,
46
  "Zero Hunger": 1
47
  },
 
48
  "max_position_embeddings": 512,
49
- "model_type": "distilbert",
50
- "n_heads": 12,
51
- "n_layers": 6,
52
  "pad_token_id": 0,
 
53
  "problem_type": "single_label_classification",
54
- "qa_dropout": 0.1,
55
- "seq_classif_dropout": 0.2,
56
- "sinusoidal_pos_embds": false,
57
- "tie_weights_": true,
58
  "torch_dtype": "float32",
59
  "transformers_version": "4.44.2",
60
- "vocab_size": 30522
 
 
61
  }
 
1
  {
2
+ "_name_or_path": "allenai/scibert_scivocab_uncased",
 
3
  "architectures": [
4
+ "BertForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
  "id2label": {
12
  "0": "No Poverty",
13
  "1": "Zero Hunger",
 
27
  "15": "Peace, Justice, and Strong Institutions"
28
  },
29
  "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
  "label2id": {
32
  "Affordable and Clean Energy": 6,
33
  "Clean Water and Sanitation": 5,
 
46
  "Sustainable Cites and Communities": 10,
47
  "Zero Hunger": 1
48
  },
49
+ "layer_norm_eps": 1e-12,
50
  "max_position_embeddings": 512,
51
+ "model_type": "bert",
52
+ "num_attention_heads": 12,
53
+ "num_hidden_layers": 12,
54
  "pad_token_id": 0,
55
+ "position_embedding_type": "absolute",
56
  "problem_type": "single_label_classification",
 
 
 
 
57
  "torch_dtype": "float32",
58
  "transformers_version": "4.44.2",
59
+ "type_vocab_size": 2,
60
+ "use_cache": true,
61
+ "vocab_size": 31090
62
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:831edb6b05738787aec4716aeaebdf938425ee32a96bb8b87e2813db16ade9ac
3
- size 267875632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:305eb5ca4d4d7a7690a5ce01bf211795b6fbd68a9fc97fd3981341d95ade3136
3
+ size 439746608
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "100": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -43,13 +43,15 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
 
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
48
- "model_max_length": 512,
 
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
- "tokenizer_class": "DistilBertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "101": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "102": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "103": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "104": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
  "unk_token": "[UNK]"
57
  }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff